From ca6b0902b8fb638794467b5ba42f8a729c189c08 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9rome=20Perrin?= <jerome@nexedi.com> Date: Tue, 10 Mar 2009 12:29:48 +0000 Subject: [PATCH] move _guessEncoding as a class method, and change a bit docstring, as it's no longer an EmailDocument method. git-svn-id: https://svn.erp5.org/repos/public/erp5/trunk@25939 20353a03-c40f-0410-a6d1-a30d3c3de9de --- product/ERP5/Document/Document.py | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/product/ERP5/Document/Document.py b/product/ERP5/Document/Document.py index d0710edde5..57f808e1b4 100644 --- a/product/ERP5/Document/Document.py +++ b/product/ERP5/Document/Document.py @@ -1273,22 +1273,22 @@ class Document(PermanentURLMixIn, XMLObject, UrlMixIn, ConversionCacheMixin, Sna mime, html = self.convert(**kw) return self._stripHTML(str(html)) + def _guessEncoding(self, string): + """ + Try to guess the encoding for this string. + Returns None if no encoding can be guessed. + """ + try: + import chardet + except ImportError: + return None + return chardet.detect(string).get('encoding', None) + def _stripHTML(self, html, charset=None): """ A private method which can be reused by subclasses to strip HTML content """ - def _guessEncoding(self, string): - """ - Some Email Clients indicate wrong encoding - This method try to guess which encoding is used. - """ - try: - import chardet - except ImportError: - return None - return chardet.detect(string).get('encoding', None) - body_list = re.findall(self.body_parser, str(html)) if len(body_list): stripped_html = body_list[0] -- 2.30.9